{"id":"https://openalex.org/W2033240004","doi":"https://doi.org/10.1109/iscslp.2014.6936667","title":"Research on generalization property of time-varying Fbank-weighted MFCC for i-vector based speaker verification","display_name":"Research on generalization property of time-varying Fbank-weighted MFCC for i-vector based speaker verification","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2033240004","doi":"https://doi.org/10.1109/iscslp.2014.6936667","mag":"2033240004"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100384935","display_name":"Jun Wang","orcid":"https://orcid.org/0009-0008-4352-6084"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9239000082015991,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7430688142776489},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7345122694969177},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7197321653366089},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.6978633403778076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662807464599609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5881607532501221},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43594372272491455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37856408953666687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3555939495563507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22302767634391785},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2142638862133026}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7430688142776489},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7345122694969177},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7197321653366089},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6978633403778076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662807464599609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5881607532501221},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43594372272491455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37856408953666687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555939495563507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22302767634391785},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2142638862133026},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2543208657","https://openalex.org/W3119288895","https://openalex.org/W2008149323","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2185075503","https://openalex.org/W4235705411","https://openalex.org/W2003046775","https://openalex.org/W202622358","https://openalex.org/W2186375278"],"abstract_inverted_index":{"MFCC":[0],"is":[1,108],"one":[2],"of":[3,21,54,73,121],"the":[4,34,55,63,71,77,86,92,104,119,142],"most":[5],"popular":[6],"features":[7],"used":[8],"in":[9,76,91,100,154],"speaker":[10,16,47],"verification,":[11],"it":[12],"involves":[13],"not":[14],"only":[15],"information,":[17],"but":[18],"also":[19],"information":[20],"contents":[22],"and":[23],"channels.":[24],"A":[25],"session-aware":[26],"Fbank":[27,59,74,95,122],"weighting":[28,60,75,96,123,137],"approach":[29],"has":[30],"been":[31],"proposed,":[32],"where":[33],"Fbanks":[35],"that":[36,46,136],"are":[37,43,50,61,117,139],"more":[38],"sensitive":[39],"to":[40,85,129],"session":[41],"variance":[42],"de-weighted":[44],"so":[45],"discriminative":[48,112],"banks":[49],"given":[51],"prominence.":[52],"Most":[53],"current":[56],"researches":[57],"on":[58],"within":[62],"GMM-UBM":[64],"framework.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,134],"study":[70],"contribution":[72],"state-of-the-art":[78],"i-vector":[79,93,101,156],"architecture.":[80],"We":[81],"found":[82],"that,":[83],"due":[84],"unsupervised":[87],"learned":[88],"loading":[89],"matrix":[90],"model,":[94],"shows":[97],"no":[98],"advantages":[99],"systems,":[102],"if":[103],"simple":[105],"cosine-distance":[106],"scoring":[107],"used.":[109],"However,":[110],"when":[111],"models":[113],"such":[114],"as":[115],"LDA/PLDA":[116],"applied,":[118],"advantage":[120],"can":[124,150],"be":[125,151],"recovered,":[126],"which":[127],"leads":[128],"significant":[130],"performance":[131],"improvement.":[132],"Meanwhile":[133],"verified":[135],"parameters":[138,143],"well":[140],"generalizable:":[141],"trained":[144,158],"with":[145,159],"a":[146,160],"small":[147],"bilingual":[148],"database":[149],"applied":[152],"successfully":[153],"another":[155],"system":[157],"large":[161],"multi-channel":[162],"database.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}